{"id":"W4411120498","doi":"10.18653/v1/2025.in2writing-1.10","title":"An Analysis of Scoring Methods for Reranking in Large Language Model Story Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Language model; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00453132,0.00004238438,0.0001899918,0.0005736389,0.0001660906,0.0000224353,0.0001037924,0.00003844559,0.00004245687],"category_scores_gemma":[0.0002638669,0.00004151616,0.0001232947,0.001310271,0.00001966934,0.0001224185,0.00001308237,0.00003962383,9.059226e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006418979,"about_ca_system_score_gemma":0.00009937408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009769876,"about_ca_topic_score_gemma":0.01647802,"domain_scores_codex":[0.9988957,0.0005550697,0.0001773243,0.0001564077,0.0001049676,0.0001105318],"domain_scores_gemma":[0.9993412,0.0003910902,0.00005237305,0.00009662551,0.00009755568,0.00002107951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000923166,0.00008755878,0.008746745,0.000009772569,0.0002728724,1.506931e-7,0.0166735,0.3944009,0.01452364,0.3915191,0.00001713585,0.1737394],"study_design_scores_gemma":[0.00009839594,0.000003458714,0.002801149,0.000003123411,0.0002135747,2.003596e-9,0.002257091,0.9896631,0.0007773962,0.003971773,0.00016666,0.00004425611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2033343,0.0001120635,0.7937628,0.0001295772,0.00003771263,0.00006989883,0.000002132692,0.00001413438,0.002537434],"genre_scores_gemma":[0.6349128,0.000004232752,0.364209,0.0000714397,0.00002551198,0.000008616345,0.00001464173,0.000001448666,0.0007523192],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5952622,"threshold_uncertainty_score":0.9195123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07331420775418603,"score_gpt":0.5180781471380161,"score_spread":0.4447639393838301,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}